中文 EN

Scan Report

Scan New Files

✓ Trusted — Risk Score 0/100
Last scan:23 hr ago Rescan
0 /100
PantryPilot
Household replenishment planning skill for mainland China that estimates what is running low, maps menus into restock demand, routes items across Meituan/PDD/Taobao, and outputs cheapest/fastest/lowest-friction restock plans
PantryPilot is a legitimate household replenishment planning skill for Chinese e-commerce platforms with no malicious behavior detected. All functionality is clearly documented, no credential harvesting, no external data exfiltration, and no hidden operations.
Skill NamePantryPilot
Duration35.5s
Enginepi
✓
Safe to install
This skill is safe for deployment. No security action required.
ResourceDeclaredInferredStatusEvidence
Filesystem NONE NONE — SKILL.md defines no filesystem access; scripts/publish.sh only modifies temp dir…
Network READ READ ✓ Aligned SKILL.md: 'inspect public product pages, grocery pages, activity pages'
Shell NONE NONE — No shell execution in skill behavior; scripts/publish.sh is build-only, not skil…
Environment NONE NONE — No environment variable access in skill implementation
Skill Invoke NONE NONE — No cross-skill invocation without user consent documented
Clipboard NONE NONE — No clipboard access documented or observed
Browser READ READ ✓ Aligned SKILL.md: 'inspect public product pages, screenshots' with explicit stop before …
Database NONE NONE — No database access documented or required

File Tree

13 files · 34.1 KB · 1107 lines
Markdown 9f · 989L Shell 1f · 69L JSON 2f · 45L YAML 1f · 4L
├─ ▾ 📁 agents
│ └─ 📋 openai.yaml YAML 4L · 397 B
├─ ▾ 📁 references
│ ├─ 📝 example-prompts.md Markdown 33L · 1.5 KB
│ ├─ 📝 output-patterns.md Markdown 30L · 659 B
│ ├─ 📝 platform-routing.md Markdown 139L · 4.1 KB
│ ├─ 📝 replenishment-framework.md Markdown 178L · 4.6 KB
│ └─ 📝 test-cases.md Markdown 62L · 1.7 KB
├─ ▾ 📁 scripts
│ └─ 🔧 publish.sh Shell 69L · 2.1 KB
├─ 📝 CHANGELOG.md Markdown 8L · 399 B
├─ 📋 clawhub.json JSON 22L · 598 B
├─ 📋 package.json JSON 23L · 506 B
├─ 📝 README.md Markdown 128L · 3.9 KB
├─ 📝 RELEASE.md Markdown 83L · 2.1 KB
└─ 📝 SKILL.md Markdown 328L · 11.6 KB

Security Positives

✓ Clear documentation of all capabilities in SKILL.md
✓ Explicit safety boundaries defined (no login, no payment, no auto-checkout)
✓ No credential harvesting or sensitive data access
✓ No external data exfiltration or C2 communication
✓ No obfuscated code or base64 payloads
✓ No suspicious file paths accessed (~/.ssh, ~/.aws, .env)
✓ Browser access limited to public pages with explicit stop conditions
✓ Standard CI/CD script for publishing only, not skill execution
✓ MIT license with transparent open-source intent